Papers › Tacotron: Towards End-to-End Speech Synthesis

Tacotron: Towards End-to-End Speech Synthesis

29 Mar 2017arXiv:1703.10135archive 2025-07-28

Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc Le, Yannis Agiomyrgiannakis, Rob Clark, Rif A. Saurous

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it's substantially faster than sample-level autoregressive methods.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 25 code samples harvested from 9 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 25 samples from 9 repositories, 16 ran (13 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 6 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

30 repositories listed; official and paper-mentioned ones first.

0fengzi0/tacotron mentioned on GitHubtfnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
CorentinJ/Real-Time-Voice-Cloning mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
IvKosar/text2speech mentioned on GitHubpytorchSyntology: not harvested report
OlaWod/my-tacotron2 mentioned on GitHubpytorchSyntology: not harvested report
ShuSQ/CCI_AP_PoseLoops mentioned on GitHubtfSyntology: not harvested report
anandaswarup/TTS mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
anandaswarup/rnn-tts mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions (arXiv:1712.05884; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
andabi/deep-voice-conversion mentioned on GitHubtfMITSyntology: 10 samples, 7 ran (0 instrument-failed) · 3 unverified report
andabi/voice-vector mentioned on GitHubtfSyntology: not harvested report
barronalex/Tacotron mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
cchinchristopherj/Concert-of-Whales mentioned on GitHubSyntology: not harvested report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
dipjyoti92/SC-WaveRNN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
dipjyoti92/TTS-Style-Transfer mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Enhancing Speech Intelligibility in Text-To-Speech Synthesis using Speaking Style Conversion (arXiv:2008.05809; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
fatchord/WaveRNN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
izzajalandoni/tts_models mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to High Fidelity Speech Synthesis with Adversarial Networks (arXiv:1909.11646; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
keithito/tacotron mentioned on GitHubtfMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
mindmapper15/Voice-Converter mentioned on GitHubtfGPL-3.0Syntology: not harvested report
mozilla/TTS mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
r9y9/tacotron_pytorch mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
racinmat/lecture-generator mentioned on GitHubtfSyntology: not harvested report
shortpoet/Final-Project mentioned on GitHubSyntology: not harvested report
thethirdwheel/malumagraph mentioned on GitHubSyntology: not harvested report
thuhcsi/tacotron mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tigthor/Voice-Cloning-AI mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
vohoaiviet/voice-vector mentioned on GitHubtfSyntology: not harvested report
Kyubyong/tacotron tfApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
TensorSpeech/TensorflowTTS tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis (arXiv:2010.05646; that paper's own run record: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
keonlee9420/Comprehensive-Tacotron2 pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings (arXiv:1910.10838; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

25 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
9ran
9unverified

Licence: 6 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

anandaswarup/TTS community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
load_checkpoint in 277 papers train_Tacotron2.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · 669fcedc80c2fee3 · report fixture: signature checkpoint_path:str/0/str, model:callable/0/?, optimizer:Adam/0/?, scaler:GradScaler/0/?, scheduler:StepLR/0/? · returned int · level recorded 2026-09-22
load_trained_model in 7 papers tts_Synthesis.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 91be03213654f639 · report fixture: signature checkpoint_path:str/0/str, model:callable/0/? · returned tuple · level recorded 2026-09-22
andabi/deep-voice-conversion community (archive-listed) 10 samples, 7 ran (0 instrument-failed) · 3 unverified
denormalize_0_1 utils.py ran fingerprinted MIT (permissive) · 47507862811320b1 · report fixture: signature normalized:ndarray/1/float, max:float/0/float, min:float/0/float · returned ndarray · level recorded 2026-09-26
merge_dict in 13 papers hparam.py ran MIT (permissive) · 0cfe2baee7e49f75 · report fixture: signature user:dict/0/?, default:dict/0/? · returned dict · level recorded 2026-09-25
normalize_0_1 utils.py ran fingerprinted MIT (permissive) · e9833fca17340113 · report fixture: signature values:ndarray/1/float, max:float/0/float, min:float/0/float · returned ndarray · level recorded 2026-09-26
read_mfcc audio.py ran MIT (permissive) · ba9b99f87a010a58 · report fixture: signature prefix:str/0/str · returned ndarray · level recorded 2026-09-26
read_spectrogram audio.py ran MIT (permissive) · ff53076f6122f01a · report fixture: signature prefix:str/0/str · returned ndarray · level recorded 2026-09-26
split_path in 5 papers utils.py ran fingerprinted MIT (permissive) · ed55468b3ae5d0b0 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-26
wav_random_crop data_load.py ran fingerprinted MIT (permissive) · 74e12237b60dba09 · report fixture: signature wav:ndarray/1/float, sr:int/0/int, duration:int/0/int · returned ndarray · level recorded 2026-09-26
conv1d in 31 papers modules.py unverified MIT (permissive) · c5f26d8500f4124f · report
load_hparam hparam.py unverified MIT (permissive) · 946edc002ef7c1b6 · report
barronalex/Tacotron community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
pad_to_dense preprocess.py ran · honoured contract no licence file found · pointer only · f3365f387e58dbeb · report fixture: signature inputs:list/1/ndarray · returned ndarray · level recorded 2026-09-22
process_char preprocess.py ran · honoured contract fingerprinted no licence file found · pointer only · 57968eca12c787ab · report fixture: signature char:str/0/str · returned int · level recorded 2026-09-22
dipjyoti92/SC-WaveRNN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
np_now in 5 papers train_tacotron.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 2af6a131384db5c8 · report fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22
fatchord/WaveRNN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
np_now in 5 papers train_tacotron.py ran · our draft was wrong MIT (permissive) · 4e3cdb2262f23b36 · report fixture: signature x:Tensor/2/float · returned ndarray · level recorded 2026-09-22
keithito/tacotron community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
expand_abbreviations in 10 papers text/cleaners.py ran fingerprinted MIT (permissive) · cea1f83e9db28ed8 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
lowercase in 9 papers text/cleaners.py ran fingerprinted MIT (permissive) · 296274b940cb0b32 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
expand_numbers in 5 papers text/cleaners.py unverified MIT (permissive) · 4c6716f6a3894fe8 · report
prenet models/modules.py unverified MIT (permissive) · 8bb2d1c4dd2ef71e · report
mozilla/TTS community (archive-listed) 1 sample, 0 ran · 1 unverified
format_data in 13 papers TTS/bin/train_tacotron.py unverified MPL-2.0 (copyleft) · pointer only · 9df2870ead7d247b · report
thuhcsi/tacotron community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
is_end_of_frames model/tacotron.py ran · violated contract fingerprinted MIT (permissive) · e882f1d97538b5c1 · report fixture: signature output:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
Kyubyong/tacotron community (archive-listed) 3 samples, 0 ran · 3 unverified
bn in 19 papers modules.py unverified Apache-2.0 (permissive) · 21f623855d3d8bb9 · report
conv1d in 31 papers modules.py unverified Apache-2.0 (permissive) · 6f9a221306ef60fb · report
embed in 13 papers modules.py unverified Apache-2.0 (permissive) · 648eb7c9f95d169e · report

Tasks

Audio SynthesisSpeech SynthesisText to SpeechText-To-Speech Synthesistext-to-speech

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Synthesis North American English Tacotron Mean Opinion Score 4.001 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CBHG, Tacotron

AdamBatch NormalizationBiGRUCBHGConvolutionDense ConnectionsDropoutGRUGriffin-Lim AlgorithmHighway LayerHighway NetworkMax PoolingReLUResidual ConnectionResidual GRUSigmoid ActivationStep DecayTacotronTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections